private static bool IsValidEnvelope(O18QuanEnvelope envelope, int charge)
{
if (envelope[0].Intensity == 0 || envelope[4].Intensity == 0)
{
return(false);
}
if (envelope[0].Charge == 0 && envelope[4].Charge == 0)
{
return(false);
}
if (envelope[0].Charge != 0 && envelope[0].Charge != charge)
{
return(false);
}
if (envelope[4].Charge != 0 && envelope[4].Charge != charge)
{
return(false);
}
return(true);
}
public O18QuantificationSummaryItem ReadFromFile(string filename)
{
var result = new O18QuantificationSummaryItem();
var root = XElement.Load(filename);
result.RawFilename = root.Element("RawFilename").Value;
var ele = root.Element("SoftwareVersion");
if (ele != null)
{
result.SoftwareVersion = ele.Value;
}
result.PeptideSequence = root.Element("PeptideSequence").Value;
result.AdditionalFormula = root.Element("AdditionalFormula").Value;
result.PeptideAtomComposition = root.Element("PeptideAtomComposition").Value;
result.PurityOfO18Water = MyConvert.ToDouble(root.Element("PurityOfO18Water").Value);
result.IsPostDigestionLabelling = bool.Parse(root.Element("IsPostDigestionLabelling").Value);
if (root.Element("TheoreticalO16Mz") != null)
{
result.TheoreticalO16Mz = MyConvert.ToDouble(root.Element("TheoreticalO16Mz").Value);
result.Charge = Convert.ToInt32(root.Element("Charge").Value);
}
result.PeptideProfile = (from x in root.Element("PeptideProfile").Elements()
let mzEle = x.Attribute("Mz")
let mz = mzEle == null ? 0.0 : MyConvert.ToDouble(mzEle.Value)
let intensity = MyConvert.ToDouble(x.Value)
select new Peak(mz, intensity)).ToList();
if (result.PeptideProfile[0].Mz == 0.0)
{
var pkls = IsotopicBuilderFactory.GetBuilder().GetProfile(new AtomComposition(result.PeptideAtomComposition), result.Charge, 10);
for (int i = 0; i < Math.Min(result.PeptideProfile.Count, pkls.Count); i++)
{
result.PeptideProfile[i].Mz = pkls[i].Mz;
result.PeptideProfile[i].Intensity = pkls[i].Intensity;
}
}
var observed = root.Element("ObservedEnvelopes");
result.ObservedEnvelopes = new List <O18QuanEnvelope>();
foreach (var pkl in observed.Elements())
{
var peakList = new O18QuanEnvelope();
int scan = int.Parse(pkl.Attribute("Scan").Value);
double retentiontime = MyConvert.ToDouble(pkl.Attribute("Retentiontime").Value);
peakList.Enabled = bool.Parse(pkl.Attribute("Enabled").Value);
peakList.IsIdentified = bool.Parse(pkl.Attribute("Identified").Value);
peakList.ScanTimes.Add(new ScanTime(scan, retentiontime));
foreach (var peak in pkl.Elements())
{
double mz = MyConvert.ToDouble(peak.Attribute("Mz").Value);
double intensity = MyConvert.ToDouble(peak.Attribute("Intensity").Value);
var p = new Peak(mz, intensity);
peakList.Add(p);
}
result.ObservedEnvelopes.Add(peakList);
}
var species = root.Element("SpeciesAbundance");
result.SpeciesAbundance.O16 = MyConvert.ToDouble(species.Element("O16").Value);
result.SpeciesAbundance.O181 = MyConvert.ToDouble(species.Element("O181").Value);
result.SpeciesAbundance.O182 = MyConvert.ToDouble(species.Element("O182").Value);
var regression = species.Element("Regression");
result.SpeciesAbundance.RegressionCorrelation = MyConvert.ToDouble(regression.Attribute("Correlation").Value);
result.SpeciesAbundance.RegressionItems.Clear();
foreach (var item in regression.Elements())
{
var ritem = new SpeciesRegressionItem();
ritem.Mz = MyConvert.ToDouble(item.Attribute("Mz").Value);
ritem.ObservedIntensity = MyConvert.ToDouble(item.Attribute("Observed").Value);
ritem.RegressionIntensity = MyConvert.ToDouble(item.Attribute("Regression").Value);
result.SpeciesAbundance.RegressionItems.Add(ritem);
}
var samples = root.Element("SampleAbundance");
result.SampleAbundance.LabellingEfficiency = MyConvert.ToDouble(samples.Attribute("LabellingEfficiency").Value);
result.SampleAbundance.Ratio = MyConvert.ToDouble(samples.Attribute("Ratio").Value);
result.SampleAbundance.O16 = MyConvert.ToDouble(samples.Element("O16").Value);
result.SampleAbundance.O18 = MyConvert.ToDouble(samples.Element("O18").Value);
return(result);
}
public override IEnumerable <string> Process(string optionFile)
{
this.options = O18QuantificationFileProcessorOptions.Load(optionFile);
var calc = options.GetProteinRatioCalculator();
var detailDirectory = options.GetDetailDirectory();
if (!Directory.Exists(detailDirectory))
{
Directory.CreateDirectory(detailDirectory);
}
var format = new MascotResultTextFormat();
IIdentifiedResult mr = format.ReadFromFile(options.ProteinFile);
CheckRawFilename(mr, optionFile);
Dictionary <string, List <IIdentifiedSpectrum> > filePepMap = GetFilePeptideMap(mr);
Dictionary <IIdentifiedPeptide, O18QuantificationSummaryItem> pepResultMap = new Dictionary <IIdentifiedPeptide, O18QuantificationSummaryItem>();
foreach (string filename in filePepMap.Keys)
{
Progress.SetMessage("Processing " + filename);
string rawFilename = filename;
if (new FileInfo(filename).Name.Equals("Cmpd.raw"))
{
rawFilename = FindRawFileName(options.ProteinFile);
}
string experimental = FileUtils.ChangeExtension(new FileInfo(rawFilename).Name, "");
using (CacheRawFile rawFile = new CacheRawFile(rawFilename))
{
int firstScanNumber = rawFile.GetFirstSpectrumNumber();
int lastScanNumber = rawFile.GetLastSpectrumNumber();
List <IIdentifiedSpectrum> peps = filePepMap[filename];
Dictionary <string, DifferentRetentionTimeEnvelopes> peptideChargeMap = new Dictionary <string, DifferentRetentionTimeEnvelopes>();
Dictionary <O18QuanEnvelopes, List <IIdentifiedSpectrum> > pklMpMap = new Dictionary <O18QuanEnvelopes, List <IIdentifiedSpectrum> >();
Progress.SetRange(0, peps.Count);
foreach (IIdentifiedSpectrum mphit in peps)
{
if (Progress.IsCancellationPending())
{
throw new UserTerminatedException();
}
Progress.Increment(1);
IIdentifiedPeptide mp = mphit.Peptide;
if (mp.Sequence.EndsWith("-"))
{
//it cannot be O18 labelled, just skip it
continue;
}
int startScan = mphit.Query.FileScan.FirstScan;
double theoreticalMz = GetTheoretialO16Mz(gapO18O16, mphit);
int theoreticalMass = (int)(theoreticalMz * mphit.Query.Charge + 0.5);
string sequenceCharge = PeptideUtils.GetPureSequence(mphit.Sequence) + "." + mphit.Query.Charge + "." + theoreticalMass;
if (!peptideChargeMap.ContainsKey(sequenceCharge))
{
peptideChargeMap.Add(sequenceCharge, new DifferentRetentionTimeEnvelopes());
}
bool bFound = false;
DifferentRetentionTimeEnvelopes pkls = peptideChargeMap[sequenceCharge];
foreach (var pklList in pkls)
{
if (pklList.Count == 0)
{
continue;
}
if (pklList[0].Scan > startScan)
{
continue;
}
if (pklList[pklList.Count - 1].Scan < startScan)
{
continue;
}
pklMpMap[pklList].Add(mphit);
bFound = true;
bool findIdentified = false;
for (int i = 1; i < pklList.Count; i++)
{
if (pklList[i].ScanTimes[0].Scan > startScan)
{
pklList[i - 1].IsIdentified = true;
findIdentified = true;
break;
}
}
if (!findIdentified)
{
pklList[pklList.Count - 1].IsIdentified = true;
}
}
if (bFound)
{
continue;
}
double mzTolerance = PrecursorUtils.ppm2mz(theoreticalMz, options.PPMTolerance);
O18QuanEnvelopes envelopes = new O18QuanEnvelopes();
bool bFirst = true;
int count = 0;
//backward
for (int scan = startScan; scan >= firstScanNumber; scan--)
{
if (1 == rawFile.GetMsLevel(scan))
{
O18QuanEnvelope envelope = GetCorrespondingEnvelope(rawFile, theoreticalMz, mphit.Query.Charge, mzTolerance, scan);
//At most one invalid scan inside both pre or post identification scan range.
if (!IsValidEnvelope(envelope, mphit.Charge))
{
if (count > 0)
{
envelopes.RemoveAt(0);
break;
}
else
{
count++;
}
}
else
{
count = 0;
}
if (bFirst)
{
envelope.IsIdentified = true;
bFirst = false;
}
envelopes.Insert(0, envelope);
}
}
if (envelopes.Count == 0)
{
//If the identified scan has no quantification information ,ignore it.
continue;
}
count = 0;
//forward
for (int scan = startScan + 1; scan <= lastScanNumber; scan++)
{
if (1 == rawFile.GetMsLevel(scan))
{
var envelope = GetCorrespondingEnvelope(rawFile, theoreticalMz, mphit.Query.Charge, mzTolerance, scan);
//At most one invalid scan inside both pre or post identification scan range.
if (!IsValidEnvelope(envelope, mphit.Charge))
{
if (count > 0)
{
envelopes.RemoveAt(envelopes.Count - 1);
break;
}
else
{
count = 1;
}
}
else
{
count = 0;
}
envelopes.Add(envelope);
}
}
if (envelopes.Count == 0)
{
continue;
}
string scanCurr = envelopes.GetScanRange();
//check scan list again
bFound = false;
foreach (var pklList in pkls)
{
if (pklList.Count == 0)
{
continue;
}
string scanOld = pklList.GetScanRange();
if (scanOld.Equals(scanCurr))
{
pklMpMap[pklList].Add(mphit);
bFound = true;
break;
}
}
if (bFound)
{
continue;
}
pkls.Add(envelopes);
pklMpMap.Add(envelopes, new List <IIdentifiedSpectrum>());
pklMpMap[envelopes].Add(mphit);
}
var detailFilePrefix = options.GetDetailDirectory() + "\\" + new FileInfo(options.ProteinFile).Name;
foreach (string sequenceCharge in peptideChargeMap.Keys)
{
DifferentRetentionTimeEnvelopes pkls = peptideChargeMap[sequenceCharge];
foreach (var envelopes in pkls)
{
if (0 == envelopes.Count)
{
continue;
}
List <IIdentifiedSpectrum> mps = pklMpMap[envelopes];
double mzTolerance = PrecursorUtils.ppm2mz(mps[0].Query.ObservedMz, options.PPMTolerance);
O18QuantificationPeptideProcessor processor = new O18QuantificationPeptideProcessor(fileFormat,
options.IsPostDigestionLabelling,
rawFilename,
PeptideUtils.GetPureSequence(mps[0].Sequence),
options.PurityOfO18Water,
envelopes, mzTolerance,
"",
options.GetScanPercentageStart() / 100,
options.GetScanPercentageEnd() / 100);
processor.TheoreticalMz = GetTheoretialO16Mz(gapO18O16, mps[0]);
processor.Charge = mps[0].Charge;
processor.SoftwareVersion = options.SoftwareVersion;
var resultFilename = MyConvert.Format("{0}.{1}.{2}.{3}.{4}.O18",
detailFilePrefix,
experimental,
PeptideUtils.GetPureSequence(mps[0].Sequence),
mps[0].Charge,
envelopes.GetScanRange());
processor.Process(resultFilename);
O18QuantificationSummaryItem item = fileFormat.ReadFromFile(resultFilename);
int maxScoreItemIndex = FindMaxScoreItemIndex(mps);
var relativeFile = Path.Combine(Path.GetFileName(options.GetDetailDirectory()), Path.GetFileName(resultFilename));
for (int i = 0; i < mps.Count; i++)
{
if (maxScoreItemIndex == i)
{
item.AssignToAnnotation(mps[i], relativeFile);
}
else
{
item.AssignDuplicationToAnnotation(mps[i], relativeFile);
}
}
}
}
}
}
List <IIdentifiedSpectrum> peptides = mr.GetSpectra();
foreach (IIdentifiedSpectrum mphit in peptides)
{
if (!mphit.Annotations.ContainsKey(O18QuantificationConstants.O18_RATIO_SCANCOUNT))
{
mphit.Annotations[O18QuantificationConstants.O18_RATIO_SCANCOUNT] = "-";
}
mphit.SetEnabled(calc.HasPeptideRatio(mphit));
}
calc.Calculate(mr, m => true);
string resultFile = FileUtils.ChangeExtension(optionFile, ".O18summary");
format.InitializeByResult(mr);
format.ProteinFormat = format.ProteinFormat.GetLineFormat(O18QuantificationConstants.O18_EXPORT_PROTEIN_HEADER);
format.WriteToFile(resultFile, mr);
Progress.SetMessage("Finished, result was saved to " + resultFile);
return(new[] { resultFile });
}
public void TestWriteToFile()
{
var item = new O18QuantificationSummaryItem();
item.RawFilename = @"D:\sqh\Science\Project/4NLFOR.raw";
item.PeptideSequence = "AFATDITDAEEDK";
item.PeptideAtomComposition = "C60H92N14O26";
item.PurityOfO18Water = 0.95;
item.PeptideProfile = IsotopicBuilderFactory.GetBuilder().GetProfile(new AtomComposition(item.PeptideAtomComposition), 1, 10);
item.ObservedEnvelopes = new List <O18QuanEnvelope> ();
var pkl1 = new O18QuanEnvelope();
pkl1.ScanTimes.Add(new ScanTime(6741, 12.34));
pkl1.Enabled = true;
pkl1.IsIdentified = true;
pkl1.Add(new Peak(713.3209, 424345.9));
pkl1.Add(new Peak(713.8254, 198378.3));
pkl1.Add(new Peak(714.3221, 246866.8));
pkl1.Add(new Peak(714.8242, 221648.0));
pkl1.Add(new Peak(715.3243, 107701.3));
pkl1.Add(new Peak(715.8316, 0.0));
item.ObservedEnvelopes.Add(pkl1);
var pkl2 = new O18QuanEnvelope();
pkl2.ScanTimes.Add(new ScanTime(6746, 13.34));
pkl2.Enabled = false;
pkl2.Add(new Peak(713.3209, 796597.7));
pkl2.Add(new Peak(713.8254, 530778.4));
pkl2.Add(new Peak(714.3221, 456099.6));
pkl2.Add(new Peak(714.8242, 339509.8));
pkl2.Add(new Peak(715.3243, 182812.3));
pkl2.Add(new Peak(715.8316, 0.0));
item.ObservedEnvelopes.Add(pkl2);
item.SpeciesAbundance = new SpeciesAbundanceInfo();
item.SpeciesAbundance.O16 = 79184307.0;
item.SpeciesAbundance.O181 = 39464386.0;
item.SpeciesAbundance.O182 = 440969.4;
item.SampleAbundance = new SampleAbundanceInfo();
item.SampleAbundance.LabellingEfficiency = 0.0219;
item.SampleAbundance.Ratio = 50;
item.SampleAbundance.O16 = 0;
item.SampleAbundance.O18 = 922867772.7;
item.SpeciesAbundance.RegressionCorrelation = 0.9999;
item.SpeciesAbundance.RegressionItems.Clear();
item.SpeciesAbundance.RegressionItems.Add(new SpeciesRegressionItem(713.3209, 36513020.6, 36512100.5));
item.SpeciesAbundance.RegressionItems.Add(new SpeciesRegressionItem(713.8254, 26438219.2, 26447909.0));
item.SpeciesAbundance.RegressionItems.Add(new SpeciesRegressionItem(714.3221, 29639265.4, 29595148.6));
item.SpeciesAbundance.RegressionItems.Add(new SpeciesRegressionItem(714.8242, 16687280.4, 16812006.0));
item.SpeciesAbundance.RegressionItems.Add(new SpeciesRegressionItem(715.3243, 7087781.0, 6823450.3));
item.SpeciesAbundance.RegressionItems.Add(new SpeciesRegressionItem(715.8316, 1799203.9, 2164120.0));
new O18QuantificationSummaryItemXmlFormat().WriteToFile(@TestContext.CurrentContext.TestDirectory + "/../../../data//O18QuantificationInformation.xml.tmp", item);
AssertUtils.AssertFileEqual(@TestContext.CurrentContext.TestDirectory + "/../../../data//O18QuantificationInformation.xml.tmp",
@TestContext.CurrentContext.TestDirectory + "/../../../data//O18QuantificationInformation.xml");
new FileInfo(@TestContext.CurrentContext.TestDirectory + "/../../../data//O18QuantificationInformation.xml.tmp").Delete();
}
